faststringbuffer.java

来自「JAVA 所有包」· Java 代码 · 共 1,295 行 · 第 1/3 页

    if (startColumn + length < m_chunkMask && m_innerFSB == null) {
      return getOneChunkString(startChunk, startColumn, length);
    }
    return getString(new StringBuffer(length), startChunk, startColumn,
                     length).toString();
  }

  protected String getOneChunkString(int startChunk, int startColumn,
                                     int length) {
    return new String(m_array[startChunk], startColumn, length);
  }

  /**
   * @param sb StringBuffer to be appended to
   * @param start Offset of first character in the range.
   * @param length Number of characters to send.
   * @return sb with the requested text appended to it
   */
  StringBuffer getString(StringBuffer sb, int start, int length)
  {
    return getString(sb, start >>> m_chunkBits, start & m_chunkMask, length);
  }

  /**
   * Internal support for toString() and getString().
   * PLEASE NOTE SIGNATURE CHANGE from earlier versions; it now appends into
   * and returns a StringBuffer supplied by the caller. This simplifies
   * m_innerFSB support.
   * <p>
   * Note that this operation has been somewhat deoptimized by the shift to a
   * chunked array, as there is no factory method to produce a String object
   * directly from an array of arrays and hence a double copy is needed.
   * By presetting length we hope to minimize the heap overhead of building
   * the intermediate StringBuffer.
   * <p>
   * (It really is a pity that Java didn't design String as a final subclass
   * of MutableString, rather than having StringBuffer be a separate hierarchy.
   * We'd avoid a <strong>lot</strong> of double-buffering.)
   *
   *
   * @param sb
   * @param startChunk
   * @param startColumn
   * @param length
   * 
   * @return the contents of the FastStringBuffer as a standard Java string.
   */
  StringBuffer getString(StringBuffer sb, int startChunk, int startColumn,
                         int length)
  {

    int stop = (startChunk << m_chunkBits) + startColumn + length;
    int stopChunk = stop >>> m_chunkBits;
    int stopColumn = stop & m_chunkMask;

    // Factored out
    //StringBuffer sb=new StringBuffer(length);
    for (int i = startChunk; i < stopChunk; ++i)
    {
      if (i == 0 && m_innerFSB != null)
        m_innerFSB.getString(sb, startColumn, m_chunkSize - startColumn);
      else
        sb.append(m_array[i], startColumn, m_chunkSize - startColumn);

      startColumn = 0;  // after first chunk
    }

    if (stopChunk == 0 && m_innerFSB != null)
      m_innerFSB.getString(sb, startColumn, stopColumn - startColumn);
    else if (stopColumn > startColumn)
      sb.append(m_array[stopChunk], startColumn, stopColumn - startColumn);

    return sb;
  }

  /**
   * Get a single character from the string buffer.
   *
   *
   * @param pos character position requested.
   * @return A character from the requested position.
   */
  public char charAt(int pos)
  {
    int startChunk = pos >>> m_chunkBits;

    if (startChunk == 0 && m_innerFSB != null)
      return m_innerFSB.charAt(pos & m_chunkMask);
    else
      return m_array[startChunk][pos & m_chunkMask];
  }

  /**
   * Sends the specified range of characters as one or more SAX characters()
   * events.
   * Note that the buffer reference passed to the ContentHandler may be
   * invalidated if the FastStringBuffer is edited; it's the user's
   * responsibility to manage access to the FastStringBuffer to prevent this
   * problem from arising.
   * <p>
   * Note too that there is no promise that the output will be sent as a
   * single call. As is always true in SAX, one logical string may be split
   * across multiple blocks of memory and hence delivered as several
   * successive events.
   *
   * @param ch SAX ContentHandler object to receive the event.
   * @param start Offset of first character in the range.
   * @param length Number of characters to send.
   * @exception org.xml.sax.SAXException may be thrown by handler's
   * characters() method.
   */
  public void sendSAXcharacters(
          org.xml.sax.ContentHandler ch, int start, int length)
            throws org.xml.sax.SAXException
  {

    int startChunk = start >>> m_chunkBits;
    int startColumn = start & m_chunkMask;
    if (startColumn + length < m_chunkMask && m_innerFSB == null) {
        ch.characters(m_array[startChunk], startColumn, length);
        return;
    }
    
    int stop = start + length;
    int stopChunk = stop >>> m_chunkBits;
    int stopColumn = stop & m_chunkMask;

    for (int i = startChunk; i < stopChunk; ++i)
    {
      if (i == 0 && m_innerFSB != null)
        m_innerFSB.sendSAXcharacters(ch, startColumn,
                                     m_chunkSize - startColumn);
      else
        ch.characters(m_array[i], startColumn, m_chunkSize - startColumn);

      startColumn = 0;  // after first chunk
    }

    // Last, or only, chunk
    if (stopChunk == 0 && m_innerFSB != null)
      m_innerFSB.sendSAXcharacters(ch, startColumn, stopColumn - startColumn);
    else if (stopColumn > startColumn)
    {
      ch.characters(m_array[stopChunk], startColumn,
                    stopColumn - startColumn);
    }
  }
  
  /**
   * Sends the specified range of characters as one or more SAX characters()
   * events, normalizing the characters according to XSLT rules.
   *
   * @param ch SAX ContentHandler object to receive the event.
   * @param start Offset of first character in the range.
   * @param length Number of characters to send.
   * @return normalization status to apply to next chunk (because we may
   * have been called recursively to process an inner FSB):
   * <dl>
   * <dt>0</dt>
   * <dd>if this output did not end in retained whitespace, and thus whitespace
   * at the start of the following chunk (if any) should be converted to a
   * single space.
   * <dt>SUPPRESS_LEADING_WS</dt>
   * <dd>if this output ended in retained whitespace, and thus whitespace
   * at the start of the following chunk (if any) should be completely
   * suppressed.</dd>
   * </dd>
   * </dl>
   * @exception org.xml.sax.SAXException may be thrown by handler's
   * characters() method.
   */
  public int sendNormalizedSAXcharacters(
          org.xml.sax.ContentHandler ch, int start, int length)
            throws org.xml.sax.SAXException
  {
	// This call always starts at the beginning of the 
    // string being written out, either because it was called directly or
    // because it was an m_innerFSB recursion. This is important since
	// it gives us a well-known initial state for this flag:
	int stateForNextChunk=SUPPRESS_LEADING_WS;

    int stop = start + length;
    int startChunk = start >>> m_chunkBits;
    int startColumn = start & m_chunkMask;
    int stopChunk = stop >>> m_chunkBits;
    int stopColumn = stop & m_chunkMask;

    for (int i = startChunk; i < stopChunk; ++i)
    {
      if (i == 0 && m_innerFSB != null)
				stateForNextChunk=
        m_innerFSB.sendNormalizedSAXcharacters(ch, startColumn,
                                     m_chunkSize - startColumn);
      else
				stateForNextChunk=
        sendNormalizedSAXcharacters(m_array[i], startColumn, 
                                    m_chunkSize - startColumn, 
																		ch,stateForNextChunk);

      startColumn = 0;  // after first chunk
    }

    // Last, or only, chunk
    if (stopChunk == 0 && m_innerFSB != null)
			stateForNextChunk= // %REVIEW% Is this update really needed?
      m_innerFSB.sendNormalizedSAXcharacters(ch, startColumn, stopColumn - startColumn);
    else if (stopColumn > startColumn)
    {
			stateForNextChunk= // %REVIEW% Is this update really needed?
      sendNormalizedSAXcharacters(m_array[stopChunk], 
																	startColumn, stopColumn - startColumn,
																	ch, stateForNextChunk | SUPPRESS_TRAILING_WS);
    }
		return stateForNextChunk;
  }
  
  static final char[] SINGLE_SPACE = {' '};
	  
  /**
   * Internal method to directly normalize and dispatch the character array.
   * This version is aware of the fact that it may be called several times
   * in succession if the data is made up of multiple "chunks", and thus
   * must actively manage the handling of leading and trailing whitespace.
   * 
   * Note: The recursion is due to the possible recursion of inner FSBs.
   *
   * @param ch The characters from the XML document.
   * @param start The start position in the array.
   * @param length The number of characters to read from the array.
   * @param handler SAX ContentHandler object to receive the event.
   * @param edgeTreatmentFlags How leading/trailing spaces should be handled. 
   * This is a bitfield contining two flags, bitwise-ORed together:
   * <dl>
   * <dt>SUPPRESS_LEADING_WS</dt>
   * <dd>When false, causes leading whitespace to be converted to a single
   * space; when true, causes it to be discarded entirely.
   * Should be set TRUE for the first chunk, and (in multi-chunk output)
   * whenever the previous chunk ended in retained whitespace.</dd>
   * <dt>SUPPRESS_TRAILING_WS</dt>
   * <dd>When false, causes trailing whitespace to be converted to a single
   * space; when true, causes it to be discarded entirely.
   * Should be set TRUE for the last or only chunk.
   * </dd>
   * </dl>
   * @return normalization status, as in the edgeTreatmentFlags parameter:
   * <dl>
   * <dt>0</dt>
   * <dd>if this output did not end in retained whitespace, and thus whitespace
   * at the start of the following chunk (if any) should be converted to a
   * single space.
   * <dt>SUPPRESS_LEADING_WS</dt>
   * <dd>if this output ended in retained whitespace, and thus whitespace
   * at the start of the following chunk (if any) should be completely
   * suppressed.</dd>
   * </dd>
   * </dl>
   *
   * 
   * @exception org.xml.sax.SAXException Any SAX exception, possibly
   *            wrapping another exception.
   */
  static int sendNormalizedSAXcharacters(char ch[], 
             int start, int length, 
             org.xml.sax.ContentHandler handler,
						 int edgeTreatmentFlags)
          throws org.xml.sax.SAXException
  {
     boolean processingLeadingWhitespace =
                       ((edgeTreatmentFlags & SUPPRESS_LEADING_WS) != 0);
     boolean seenWhitespace = ((edgeTreatmentFlags & CARRY_WS) != 0);
     boolean suppressTrailingWhitespace =
                       ((edgeTreatmentFlags & SUPPRESS_TRAILING_WS) != 0);
     int currPos = start;
     int limit = start+length;

     // Strip any leading spaces first, if required
     if (processingLeadingWhitespace) {
         for (; currPos < limit
                && XMLCharacterRecognizer.isWhiteSpace(ch[currPos]);
              currPos++) { }

         // If we've only encountered leading spaces, the
         // current state remains unchanged
         if (currPos == limit) {
             return edgeTreatmentFlags;
         }
     }

     // If we get here, there are no more leading spaces to strip
     while (currPos < limit) {
         int startNonWhitespace = currPos;

         // Grab a chunk of non-whitespace characters
         for (; currPos < limit
                && !XMLCharacterRecognizer.isWhiteSpace(ch[currPos]);
              currPos++) { }

         // Non-whitespace seen - emit them, along with a single
         // space for any preceding whitespace characters
         if (startNonWhitespace != currPos) {
             if (seenWhitespace) {
                 handler.characters(SINGLE_SPACE, 0, 1);
                 seenWhitespace = false;
             }
             handler.characters(ch, startNonWhitespace,
                                currPos - startNonWhitespace);
         }

         int startWhitespace = currPos;

         // Consume any whitespace characters
         for (; currPos < limit
                && XMLCharacterRecognizer.isWhiteSpace(ch[currPos]);
              currPos++) { }

         if (startWhitespace != currPos) {
             seenWhitespace = true;
         }
     }

     return (seenWhitespace ? CARRY_WS : 0)
            | (edgeTreatmentFlags & SUPPRESS_TRAILING_WS);
  }

  /**
   * Directly normalize and dispatch the character array.
   *
   * @param ch The characters from the XML document.
   * @param start The start position in the array.
   * @param length The number of characters to read from the array.
   * @param handler SAX ContentHandler object to receive the event.
   * @exception org.xml.sax.SAXException Any SAX exception, possibly
   *            wrapping another exception.
   */
  public static void sendNormalizedSAXcharacters(char ch[], 
             int start, int length, 
             org.xml.sax.ContentHandler handler)
          throws org.xml.sax.SAXException
  {
		sendNormalizedSAXcharacters(ch, start, length, 
             handler, SUPPRESS_BOTH);
	}
		
	/**
   * Sends the specified range of characters as sax Comment.
   * <p>
   * Note that, unlike sendSAXcharacters, this has to be done as a single 
   * call to LexicalHandler#comment.
   *
   * @param ch SAX LexicalHandler object to receive the event.
   * @param start Offset of first character in the range.
   * @param length Number of characters to send.
   * @exception org.xml.sax.SAXException may be thrown by handler's
   * characters() method.
   */
  public void sendSAXComment(
          org.xml.sax.ext.LexicalHandler ch, int start, int length)
            throws org.xml.sax.SAXException
  {

    // %OPT% Do it this way for now...
    String comment = getString(start, length);
    ch.comment(comment.toCharArray(), 0, length);
  }

  /**
   * Copies characters from this string into the destination character
   * array.
   *
   * @param      srcBegin   index of the first character in the string
   *                        to copy.
   * @param      srcEnd     index after the last character in the string
   *                        to copy.
   * @param      dst        the destination array.
   * @param      dstBegin   the start offset in the destination array.
   * @exception IndexOutOfBoundsException If any of the following
   *            is true:
   *            <ul><li><code>srcBegin</code> is negative.
   *            <li><code>srcBegin</code> is greater than <code>srcEnd</code>
   *            <li><code>srcEnd</code> is greater than the length of this
   *                string
   *            <li><code>dstBegin</code> is negative
   *            <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
   *                <code>dst.length</code></ul>
   * @exception NullPointerException if <code>dst</code> is <code>null</code>
   */
  private void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin)
  {
    // %TBD% Joe needs to write this function.  Make public when implemented.
  }

  /**
   * Encapsulation c'tor. After this is called, the source FastStringBuffer
   * will be reset to use the new object as its m_innerFSB, and will have
   * had its chunk size reset appropriately. IT SHOULD NEVER BE CALLED
   * EXCEPT WHEN source.length()==1<<(source.m_chunkBits+source.m_rebundleBits)
   *
   * NEEDSDOC @param source
   */
  private FastStringBuffer(FastStringBuffer source)
  {

    // Copy existing information into new encapsulation
    m_chunkBits = source.m_chunkBits;
    m_maxChunkBits = source.m_maxChunkBits;
    m_rebundleBits = source.m_rebundleBits;
    m_chunkSize = source.m_chunkSize;
    m_chunkMask = source.m_chunkMask;
    m_array = source.m_array;
    m_innerFSB = source.m_innerFSB;

    // These have to be adjusted because we're calling just at the time
    // when we would be about to allocate another chunk
    m_lastChunk = source.m_lastChunk - 1;
    m_firstFree = source.m_chunkSize;

    // Establish capsule as the Inner FSB, reset chunk sizes/addressing
    source.m_array = new char[16][];
    source.m_innerFSB = this;

    // Since we encapsulated just as we were about to append another
    // chunk, return ready to create the chunk after the innerFSB
    // -- 1, not 0.
    source.m_lastChunk = 1;
    source.m_firstFree = 0;
    source.m_chunkBits += m_rebundleBits;
    source.m_chunkSize = 1 << (source.m_chunkBits);
    source.m_chunkMask = source.m_chunkSize - 1;
  }
}